A novel diagnostic target in the hepatitis C virus genome

Abstract

Background: Detection and quantification of hepatitis C virus (HCV) RNA is integral to diagnostic and therapeutic regimens. All molecular assays target the viral 5'-noncoding region (5'-NCR), and all show genotype-dependent variation of sensitivities and viral load results. Non-western HCV genotypes have been under-represented in evaluation studies. An alternative diagnostic target region within the HCV genome could facilitate a new generation of assays.

Methods and findings: In this study we determined by de novo sequencing that the 3'-X-tail element, characterized significantly later than the rest of the genome, is highly conserved across genotypes. To prove its clinical utility as a molecular diagnostic target, a prototype qualitative and quantitative test was developed and evaluated multicentrically on a large and complete panel of 725 clinical plasma samples, covering HCV genotypes 1-6, from four continents (Germany, UK, Brazil, South Africa, Singapore). To our knowledge, this is the most diversified and comprehensive panel of clinical and genotype specimens used in HCV nucleic acid testing (NAT) validation to date. The lower limit of detection (LOD) was 18.4 IU/ml (95% confidence interval, 15.3-24.1 IU/ml), suggesting applicability in donor blood screening. The upper LOD exceeded 10(-9) IU/ml, facilitating viral load monitoring within a wide dynamic range. In 598 genotyped samples, quantified by Bayer VERSANT 3.0 branched DNA (bDNA), X-tail-based viral loads were highly concordant with bDNA for all genotypes. Correlation coefficients between bDNA and X-tail NAT, for genotypes 1-6, were: 0.92, 0.85, 0.95, 0.91, 0.95, and 0.96, respectively; X-tail-based viral loads deviated by more than 0.5 log10 from 5'-NCR-based viral loads in only 12% of samples (maximum deviation, 0.85 log10). The successful introduction of X-tail NAT in a Brazilian laboratory confirmed the practical stability and robustness of the X-tail-based protocol. The assay was implemented at low reaction costs (US$8.70 per sample), short turnover times (2.5 h for up to 96 samples), and without technical difficulties.

Conclusion: This study indicates a way to fundamentally improve HCV viral load monitoring and infection screening. Our prototype assay can serve as a template for a new generation of viral load assays. Additionally, to our knowledge this study provides the first open protocol to permit industry-grade HCV detection and quantification in resource-limited settings.

Figure 1. Nucleotide Similarities within HCV 5′- and 3′-Genome Ends

Top panel: schematic representation of the HCV reference genome H77 as given in the 2008 LANL database. Bottom panel: Percent nucleotide identity along the 5′-NCR and the X-tail, as calculated by a sliding window analysis with VectorNTI software. Window size was 2 nucleotides. The alignment used for the sliding window analysis contained the complete HCV genotype reference panel (n = 60 sequences) from the LANL HCV database (available at http://hcv.lanl.gov/content/sequence/NEWALIGN/align.html) and all X-tail sequences available in GenBank as shown in Text S2, including the sequences determined de novo in this study (EU835523-EU835532).

Figure 2. Secondary Structure Predictions

Secondary structure of the HCV 5′-NCR (A) and the 3′-X-tail (B) of HCV 1a reference genome H77 as predicted by MFOLD [43]. Prediction was done at 50 mM salt concentration and PCR primer annealing temperature (58 °C). Free energies ΔG were −1.6 × 10⁻³ J/mol for (A) and −5,06 × 10⁻⁴ J/mol for (B). 5′-NCR structure predictions were identical for all genotypes in the LANL genotype reference panel except genotype 2, which had one additional stem-loop element (not covered by primers, not shown in [A]). Structure predictions for all X-tail sequences (database and new sequences) were identical (not shown in [B]). (A) Binding sites of oligonucleotides used by the Roche Amplicor assay are shown in red (sense primer KY80, hybridization probe KY150, antisense primer KY78). Nucleotide variability at these binding sites is shown in Text S2). (B) Outer lines in red identify the hybridization sites of oligonucleotides used in initial X-tail RT-PCR set, yielding limited sensitivity (forward primer F5, TaqMan probe P1, reverse primer R7). Interior lines in green identify the final X-tail prototype assay (forward primer F5, reverse primer R2, probe MGB2). Nucleotide variability at these sites is shown in Text S2.

Figure 3. Correlation of Viral Loads as Determined by X-Tail RT-PCR (x-Axis) and bDNA (y-Axis)

Genotypes and numbers of samples (n) are given in the bottom right corner of each panel. Pearson's bivariate correlation coefficients were 0.92, 0.85, 0.95, 0.91, 0.95, and 0.96 for HCV genotypes 1 to 6, respectively. The dashed lines represent ideal correlations. Genotype 5, 0.07/0.31; and genotype 6, 0.12/0.19.

Figure 4. Quantitative Deviations between X-Tail–Based and bDNA Viral Loads, per Genotype (y-Axis)

Genotypes are indicated below the x-axis, the number of samples tested per genotype (n) above the x-axis. Each box shows the median, interquartile range (box length, containing 50% of data) and whiskers show extreme values (there were no statistical outliers). Deviations between X-tail RT-PCR and bDNA [log10 X-tail RT-PCR − log10 bDNA] were genotype 1, 0.00/0.31 (mean/SD); genotype 2, 0.01/0.33; genotype 3, 0.17/0.32; genotype 4, −0.09/0.37; genotype 5, 0.07/0.31; and genotype 6, 0.12/0.19.

Figure 5. Results Obtained with X-Tail Viral Load Monitoring, Implemented in Brazil

127 samples were measured in a Brazilian HIV-1 viral load monitoring centre by Bayer VERSANT 3.0 HCV bDNA assay and by X-tail in-house PCR. (A) Correlation of viral loads between X-tail RT-PCR (x-axis) and Bayer bDNA 3.0 (y-axis). The dashed line represents an ideal correlation. Pearson's bivariate correlation coefficient was 0.97. (B) Quantitative differences. The box shows the median and interquartile range (box length). The whiskers represent an extension of the 25th or 75th percentiles by 1.5 times the interquartile range. Datum points beyond the whisker range are considered as outliers and marked as asterisks.